© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112532
    Prev
    Next
    INDEX
    Explanations

    citations and affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Füßen
    -1.97
    {
    -1.68
     seleccionadas
    -1.66
    chyma
    -1.63
    .
    -1.63
     permitir
    -1.49
     bloquer
    -1.48
     The
    -1.48
     relacionadas
    -1.47
     asegu
    -1.46
    POSITIVE LOGITS
     who
    1.85
    ’
    1.80
    してきました
    1.73
    ↵
    1.63
    ᠁
    1.55
     più
    1.52
     a
    1.50
     intend
    1.48
     then
    1.47
    }.
    1.45
    Activations Density 0.009%

    No Known Activations